Forced Out of Our Homelands

Exploring UNHCR Data on Forced Displacement to Predict Asylum Acceptance Rates

Maria Mohyuddin and Aarushi Tripathi

Exploring the Data

2022 has been one of the worst years

  • In 2022, millions were forcibly displaced by persecution, conflict, violence, human rights violations and events seriously disturbing public order

  • The numbers grew by 21% by the end of the year

  • More than 1 in 74 people worldwide remained forcibly displaced as a result

  • Almost 90 per cent of them in low- and middle-income countries

Top 10 Countries of Origin for Refugees

Important Definitions

Refugees include individuals granted complementary forms of protection, and those enjoying temporary protection.

Asylum-seekers are individuals who have sought international protection and whose claims for refugee status have not yet been determined.

Other people in need of international protection refers to people who are outside their country or territory of origin, typically because they have been forcibly displaced across international borders, who have not been reported under other categories but who likely need international protection.

Internally displaced persons are persons who have been forced to flee their homes , in particular as a result of, or in order to avoid the effects of armed conflict, situations of generalized violence, violations of human rights or natural or human-made disasters, and who have not crossed an internationally recognized State border.

In the last decade, 62.2 million refugees were added

Which Nations Do Displaced People Belong To?

Refugee Population Across UNHCR Regions

Applications

Which Countries Accept Most Asylum Applications

Most Common Types of Applications

Predicting Acceptance Rates

Model Used and Design- Dependent and Independent Vars

  • Dependent Variable: Acceptance Rate
  • Independent Variables: ISO Codes for Countries of Origin and Asylum, Procedure Type, Decision Level, Applicant Type
  • Random forest because of categorical input
  • 0.283
  • Improved RMSE value since last run
  • Ideal parameters based on tuning- 3 predictors (mtry) and 28 data points in a node (min_n)

THANK YOU!